Measure-theoretic Approaches and Optimal Transportation in Statistics

Thematic program with short courses, seminars and workshops

The Wasserstein distance in Optimal transportation has proved to be useful for a wide range of learning tasks such as generative models, domain adaptation or supervised embeddings. It is also an important metric for Topological Data Analysis and Geometric inference. More generally, distances on the space of probability measures, such as the maximum mean discrepancy, have shown to be powerful tools in statistical learning.

This workshop is part of a series of events throughout the fall: IHP Geometry and Statistics in Data Sciences which will include courses that will be posted online soon.

Invited Speakers

Quentin Berthet (Google Research)
Blanche Buet (LMO, Orsay)
Elsa Cazelles (IRIT, Toulouse)
Nicolas Courty (IRISA, Rennes)
Agnès Desolneux (Centre Borelli, Saclay)
Arthur Gretton (UCL, London)
Anna Korba (CREST, Saclay)
Thibaut Le Gouic (IMM, Marseille)
Christophe Ley (Ghent University)
Jean-Michel Loubes (IMT, Toulouse)
Olga Mula (CEREMADE, Dauphine)
Axel Munk (Göttingen & Planck)
Quentin Paris (HSE, Moscow)
Giovanni Peccati (Luxemburg)
Gabriel Peyré (DMA, ÉNS)
Johan Segers (UC Louvain)
Bodhisattva Sen (Columbia, New York)

Organizers: Eddie Aamari (LPSM, CNRS), Catherine Aaron (LMBP, Université Clermont Auvergne) Frédéric Chazal (LMO, INRIA), Aurélie Fischer (LPSM, Université de Paris) Marc Hoffmann (CEREMADE, Paris Dauphine), Alice Le Brigant (SAMM, Paris 1 Panthéon Sorbonne) Clément Levrard (LPSM, Université de Paris), Bertrand Michel (LMJL, Ecole Centrale Nantes)